© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 6689
    Prev
    Next
    INDEX
    Explanations

    references to age or the term "old."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.69
    bootstrapcdn
    -0.66
    +#+
    -0.62
    CppMethod
    -0.60
     TextAppearance
    -0.55
    IntoConstraints
    -0.53
    astify
    -0.49
    XmlAccessorType
    -0.49
    mybatisplus
    -0.47
     jScrollPane
    -0.47
    POSITIVE LOGITS
     old
    1.63
     Old
    1.47
    Old
    1.45
     OLD
    1.42
     vieux
    1.31
     vieilles
    1.28
    old
    1.27
     vieja
    1.23
     vecchia
    1.23
     vecchio
    1.22
    Activations Density 0.032%

    No Known Activations